Snapshot the current ~/.claude.json as a named profile so it can be restored later via switch_profile.
AI agents use save_profile to create or update resources in Claude Code Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Code Toolkit environment.
save_profile creates and modifies data (a new named profile storing configuration) but does so reversibly. It does not execute arbitrary code, delete data, or commit financial actions. The medium severity reflects that misuse could create unwanted configuration profiles or consume storage, but the action itself is non-destructive and can be undone via cleanup or profile switching.
From the tool's definition Tool creates or stores a named snapshot/profile of configuration data (described as "Snapshot the current ~/.claude.json as a named profile"). This is a reversible write operation that persists configuration state without destructive intent.
Documented attack patterns abuse exactly the kind of access save_profile gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for save_profile:
{
"version": "1",
"default": "deny",
"tools": {
"save_profile": {
"limits": [
{
"counter": "save_profile_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_profile stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Snapshot the current ~/.claude.json as a named profile so it can be restored later via switch_profile. It is categorised as a Write tool in the Claude Code Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Code Toolkit MCP server in PolicyLayer and add a rule for save_profile: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Code Toolkit. Nothing to install.
save_profile is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_profile rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for save_profile. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
save_profile is provided by the Claude Code Toolkit MCP server (asifkibria/claude-code-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code Toolkit, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
40 Claude Code Toolkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.